System and method for controlling an operation of a robotic arm

Abstract

The present disclosure discloses a system and a method for controlling an operation of a robotic arm holding a tool for manipulating object. The method comprises collecting measurements of tactile sensors associated with the robotic arm, estimating, based on the collected measurements and constraints enforced by a Model Predictive Controller (MPC), a feedback signal indicative of a pose of the object, and executing the MPC configured to produce, based on the pose of the object, control commands for actuators of the robotic arm by optimizing a cost function minimizing a deviation of the pose of the object from a target pose of the object. The optimization of the cost function is subject to the constraints that constrain one or more forces acting on the object at one or more point of contacts to be within corresponding friction regions. The method further comprises controlling the actuators according to the control commands.

The invention claimed is: 
     
       1. A control system for controlling an operation of a robotic arm holding a tool for manipulating an object, comprising: at least one processor;
 and a memory having instructions stored thereon that cause the at least one processor of the control system to: 
 collect measurements of at least one tactile sensor associated with the robotic arm; 
 estimate, based on the collected measurements and constraints enforced by a Model Predictive Controller (MPC), a feedback signal indicative of a pose of the object; 
 execute the MPC configured to produce, based on the estimated pose of the object, control commands for actuators of the robotic arm by optimizing a cost function minimizing a deviation of the pose of the object from a target pose of the object, wherein the optimization of the cost function is subject to the constraints, and wherein the constraints constrain one or more forces acting on the object at one or more point of contacts to be within corresponding friction regions, wherein a shape of the friction region is based on a shape of the object; and 
 control the actuators of the robotic arm according to the control commands. 
 
     
     
       2. The control system of  claim 1 , wherein the one or more point of contacts include a contact between the object and the tool and a contact between the object and an environment. 
     
     
       3. The control system of  claim 1 , wherein the constraints include a quasi-static equilibrium of the tool and the object with zero slippage at the one or more point of contacts. 
     
     
       4. The control system of  claim 1 , wherein the processor is further configured to collect measurements of robot proprioception and the measurements of the at least one tactile sensor. 
     
     
       5. The control system of  claim 4 , wherein the measurements of robot proprioception include values of one or more of a motor speed, robotic arm joint angles, and a battery voltage of the robotic arm. 
     
     
       6. The control system of  claim 4 , wherein the processor is further configured to:
 compute, based on the measurements of the at least one tactile sensor, a relative orientation of frame at center of grasp of the object; and 
 execute, using the measurements of robot proprioception and the relative orientation of frame at center of grasp of the object, a least-squares regression to estimate the pose of the object. 
 
     
     
       7. A method for controlling an operation of a robotic arm holding a tool for manipulating an object, comprising:
 collecting measurements of at least one tactile sensor associated with the robotic arm; 
 estimating, based on the collected measurements and constraints enforced by a Model Predictive Controller (MPC), a feedback signal indicative of a pose of the object; 
 executing the MPC configured to produce, based on the estimated pose of the object, control commands for actuators of the robotic arm by optimizing a cost function minimizing a deviation of the pose of the object from a target pose of the object, wherein the optimization of the cost function is subject to the constraints, and wherein the constraints constrain one or more forces acting on the object at one or more point of contacts to be within corresponding friction regions, wherein a shape of the friction region is based on a shape of the object; and 
 controlling the actuators of the robotic arm according to the control commands. 
 
     
     
       8. The method of  claim 7 , wherein the one or more point of contacts include a contact between the object and the tool and a contact between the object and an environment. 
     
     
       9. The method of  claim 7 , wherein the constraints include a quasi-static equilibrium of the tool and the object with zero slippage at the one or more point of contacts. 
     
     
       10. The method of  claim 7 , wherein the method further comprises collecting measurements of robot proprioception and the measurements of the at least one tactile sensor. 
     
     
       11. The method of  claim 10 , wherein the measurements of robot proprioception include values of one or more of a motor speed, robotic arm joint angles, and a battery voltage of the robotic arm. 
     
     
       12. The method of  claim 10 , wherein the method further comprises:
 computing, based on the measurements of the at least one tactile sensor, a relative orientation of frame at center of grasp of the object; and 
 executing, using the measurements of robot proprioception and the relative orientation of frame at center of grasp of the object, a least-squares regression to estimate the pose of the object. 
 
     
     
       13. A non-transitory computer-readable storage medium embodied thereon a program executable by a processor for performing a method for controlling an operation of a robotic arm holding a tool for manipulating an object, the method comprising:
 collecting measurements of at least one tactile sensor associated with the robotic arm; 
 estimating, based on the collected measurements and constraints enforced by a Model Predictive Controller (MPC), a feedback signal indicative of a pose of the object; 
 executing the MPC configured to produce, based on the estimated pose of the object, control commands for actuators of the robotic arm by optimizing a cost function minimizing a deviation of the pose of the object from a target pose of the object, wherein the optimization of the cost function is subject to the constraints, and wherein the constraints constrain one or more forces acting on the object at one or more point of contacts to be within corresponding friction regions, wherein a shape of the friction region is based on a shape of the object; and 
 controlling the actuators of the robotic arm according to the control commands. 
 
     
     
       14. The non-transitory computer-readable storage medium of  claim 13 , wherein the one or more point of contacts include a contact between the object and the tool and a contact between the object and an environment. 
     
     
       15. The non-transitory computer-readable storage medium of  claim 13 , wherein the constraints include a quasi-static equilibrium of the tool and the object with zero slippage at the one or more point of contacts. 
     
     
       16. The non-transitory computer-readable storage medium of  claim 13 , wherein the method further comprises collecting measurements of robot proprioception and the measurements of the at least one tactile sensor. 
     
     
       17. The non-transitory computer-readable storage medium of  claim 16 , wherein the method further comprises:
 computing, based on the measurements of the at least one tactile sensor, a relative orientation of frame at center of grasp of the object; and 
 executing, using the measurements of robot proprioception and the relative orientation of frame at center of grasp of the object, a least-squares regression to estimate the pose of the object. 
 
     
     
       18. A control system for controlling an operation of a robotic arm holding a tool for manipulating an object, comprising: at least one processor; and a memory having instructions stored thereon that cause the at least one processor of the control system to:
 collect measurements of at least one tactile sensor associated with the robotic arm and measurements of robot proprioception; 
 compute, based on the measurements of the at least one tactile sensor, a relative orientation of frame at center of grasp of the object: 
 execute, using the measurements of robot proprioception and the relative orientation of frame at center of grasp of the object, a least-squares regression to estimate the pose of the object; 
 estimate, based on the collected measurements and constraints enforced by a Model Predictive Controller (MPC), a feedback signal indicative of a pose of the object; 
 execute the MPC configured to produce, based on the estimated pose of the object, control commands for actuators of the robotic arm by optimizing a cost function minimizing a deviation of the pose of the object from a target pose of the object, wherein the optimization of the cost function is subject to the constraints, and wherein the constraints constrain one or more forces acting on the object at one or more point of contacts to be within corresponding friction regions; and 
 control the actuators of the robotic arm according to the control commands. 
 
     
     
       19. A method for controlling an operation of a robotic arm holding a tool for manipulating an object, comprising:
 collecting measurements of at least one tactile sensor associated with the robotic arm and measurements of robot proprioception; 
 computing, based on the measurements of the at least one tactile sensor, a relative orientation of frame at center of grasp of the object; 
 executing, using the measurements of robot proprioception and the relative orientation of frame at center of grasp of the object, a least-squares regression to estimate the pose of the object; 
 estimating, based on the collected measurements and constraints enforced by a Model Predictive Controller (MPC), a feedback signal indicative of a pose of the object; 
 executing the MPC configured to produce, based on the estimated pose of the object, control commands for actuators of the robotic arm by optimizing a cost function minimizing a deviation of the pose of the object from a target pose of the object, wherein the optimization of the cost function is subject to the constraints, and wherein the constraints constrain one or more forces acting on the object at one or more point of contacts to be within corresponding friction regions; and 
 controlling the actuators of the robotic arm according to the control commands. 
 
     
     
       20. A non-transitory computer-readable storage medium embodied thereon a program executable by a processor for performing a method for controlling an operation of a robotic arm holding a tool for manipulating an object, the method comprising:
 collecting measurements of at least one tactile sensor associated with the robotic arm and measurements of robot proprioception; 
 computing, based on the measurements of the at least one tactile sensor, a relative orientation of frame at center of grasp of the object; 
 executing, using the measurements of robot proprioception and the relative orientation of frame at center of grasp of the object, a least-squares regression to estimate the pose of the object; 
 estimating, based on the collected measurements and constraints enforced by a Model Predictive Controller (MPC), a feedback signal indicative of a pose of the object; 
 executing the MPC configured to produce, based on the estimated pose of the object, control commands for actuators of the robotic arm by optimizing a cost function minimizing a deviation of the pose of the object from a target pose of the object, wherein the optimization of the cost function is subject to the constraints, and wherein the constraints constrain one or more forces acting on the object at one or more point of contacts to be within corresponding friction regions; and 
 controlling the actuators of the robotic arm according to the control commands.